Category

Best AI and LLM engineering skills, page 13

Skills #577–624 of 5,040, ranked by score.

AI & LLM Engineering skills, ranked

Ranked by score. Sort bymost stars,trending,newest,recently updated

AI & LLM Engineering skills, ranked
#SkillRepositoryStarsUsed inTokensAuto-checkLicenceUpdated
577

Answer "where did I stop?" for this project. An agent skill from Avijit07x/claude-db.

Avijit07x/claude-db233—~604Automated safety check: PassApache-2.0today
578

DeepSeek API 助手 - 编程辅助、模型选择、API调用指南、定价信息. An agent skill from dongsheng123132/u-claw.

dongsheng123132/u-claw1.8k—~367Automated safety check: PassMIT4 days ago
579

Render videos and pictures on a ComfyUI server that has the Continuity node pack (MiniMax H3, LTX 2.5, Krea 2, Ideogram 4, Qwen Image, Flux 2 Klein) with one command, the render.py bundled in this…

roadmaus/ComfyUI-Continuity133—~1.7kAutomated safety check: PassMIT3 days ago
580

Governance behavior for AI agents governed by DashClaw. An agent skill from ucsandman/DashClaw.

ucsandman/DashClaw311—~2.7kAutomated safety check: PassMITyesterday
581

Generate synthetic data using sdghub with composable blocks and YAML flows.

Red-Hat-AI-Innovation-Team/sdg_hub164—~3.1kAutomated safety check: PassApache-2.02 days ago
582

Create and manage dstack presets: a toolkit that streamlines model inference optimization with agents, and a portable preset format.

dstackai/dstack2.3k—~403Automated safety check: PassMPL-2.02 days ago
583

Always resolve Hugging Face models via model-shelf before any download.

alexziskind1/model-shelf130—~792Automated safety check: PassMIT1 mo ago
584

A skill your agent uses when implementing any endpoint, form handler, CLI tool, or function that accepts external input.

aiming-lab/MetaClaw3.5k—~251Automated safety check: PassMIT4 mo ago
585
585.Fde

Keeps the engagement record for client work. An agent skill from suboss87/FDEOps.

suboss87/FDEOps957—~2.9kAutomated safety check: PassMIT2 days ago
586
586.Slab

Writing, editing, and rendering Slab documents (.slab) — the declarative design language for app screens, posters, terminal UIs, and interactive components.

stencil-hq/slab114—~3.1kAutomated safety check: PassMIT1 mo ago
587

Expert guidance for fast fine-tuning with Unsloth - 2-5x faster training, 50-80% less memory, LoRA/QLoRA optimization

Orchestra-Research/AI-Research-SKILLs13k10 repos~577Automated safety check: PassMIT3 mo ago
588

Turns a natural-language description of routing intent into a valid Lemonade collection.router policy JSON.

amd/skills408—~4kAutomated safety check: PassMITyesterday
589
589.Review SkillOfficial

Review a proposed Agent Skill for structural validity and content quality before publishing.

mongodb/agent-skills189—~1.5kAutomated safety check: NotesApache-2.0yesterday
590

Mine AI coding-agent session transcripts into structured, gate-validated GPU-kernel optimization records for the wiki.

alibaba/atrex-kernel-agent168—~3.1kAutomated safety check: PassApache-2.0yesterday
591

Explains how to load text, files, folders, URLs, repositories and databases into cognee memory with remember(), including datasets, extractors and tags.

topoteretes/cognee32k—~2.6kAutomated safety check: NotesApache-2.0yesterday
592

Create, build, validate, and upload a Packs SDK agent (pack.ts using sdk.newAgent()) to your Coda/Superhuman account, including registering an API token, wiring up tools…

coda/packs-sdk112—~2.2kAutomated safety check: PassMITyesterday
593

Walks through releasing a new datadog-lambda-js Lambda layer version — the automated Commercial release (version bump, tag, GitLab sign/publish jobs, npm publish, GitHub release) and the manual…

DataDog/datadog-lambda-js126—~1.8kAutomated safety check: PassApache-2.02 days ago
594

Capture a Nsight Systems (.nsys-rep) profile of a short PithTrain run for performance analysis.

mlc-ai/pith-train355—~1kAutomated safety check: PassApache-2.02 days ago
595

Create original, material-reference-driven, consistent, photorealistic character casting sheets for commercial, advertising, cinematic, model, occupational, everyday, historical…

dacnay816y62-hub/character-casting-studio-skill126—~6.6kAutomated safety check: PassNo licence1 mo ago
596

Profile CUDA kernels with Nsight Compute on B200 / sm100. An agent skill from mit-han-lab/ncu-report-skill.

mit-han-lab/ncu-report-skill251—~2kAutomated safety check: PassMIT1 mo ago
597

A skill your agent uses when adding a new optimized kernel or operator to veomni/ops/.

ByteDance-Seed/VeOmni2.2k—~3.1kAutomated safety check: PassApache-2.0yesterday
598
598.Openma

Use the openma platform to build, deploy, and manage AI agents.

openma-ai/open-managed-agents315—~854Automated safety check: PassApache-2.0today
599

Sets up and runs side-by-side model evaluations with frozen questions, isolated tools and traceable results, using your own question bank or benchmark subsets.

liucongg/liucong-skills248—~752Automated safety check: PassApache-2.01 mo ago
600

Build DSPy 3.2.x programs through spec, program, metric and baseline; extend to optimization and export when requested and justified by task budget.

intertwine/dspy-agent-skills278—~1.7kAutomated safety check: PassMIT1 mo ago
601

Prepare the environment and run the LLM-driven agent evals (e2e/agent-evals/) against a chosen sim-use binary.

lycorp-jp/sim-use1.4k—~1.4kAutomated safety check: PassApache-2.02 days ago
602

Train custom LoRAs with ostris AI-Toolkit. An agent skill from artokun/comfyui-mcp.

artokun/comfyui-mcp803—~2.7kAutomated safety check: PassMIT6 days ago
603

Run Python unit test suites strictly using the uv package manager and pytest.

brendanhasz/probflow175—~657Automated safety check: PassMIT14 days ago
604

X/Twitter public sentiment research. An agent skill from edinetdb/dexter-jp.

edinetdb/dexter-jp312—~789Automated safety check: PassMIT2 days ago
605

Audit and improve the prompt surface of Avibe Agents across backends (Claude, Codex/GPT, OpenCode) — global and project rules, Agent system prompts, Skills, delegation briefs, and Task and Watch…

avibe-bot/avibe624—~2.9kAutomated safety check: PassMITtoday
606

Designs clear, testable prompts for agent workflows. An agent skill from repowise-dev/claude-code-prompts.

repowise-dev/claude-code-prompts1.2k—~231Automated safety check: PassMIT5 mo ago
607

Create specialized Claude Code sub-agents with custom system prompts and tool configurations.

greatSumini/cc-system438—~958Automated safety check: PassMIT4 mo ago
608

Triage and repair hipfire runtime failures such as daemon hangs, stale serve.pid, port 11435 conflicts, ROCm include-path problems, missing precompiled kernels, VRAM OOM, kernel JIT failures, and…

warpfront/hipfire658—~1.4kAutomated safety check: PassUnknownyesterday
609

A skill your agent uses when the user has changed a prompt (system prompt, RAG template, agent instruction, etc.) and wants to know whether the candidate is better or worse than the baseline.

agentscope-ai/OpenJudge871—~2.8kAutomated safety check: PassApache-2.01 mo ago
610

Imports and registers subgraph blueprints into the ComfyUI workflowtemplates repository.

Comfy-Org/workflow_templates1.3k—~1.5kAutomated safety check: PassMITtoday
611

Comprehensive guide for designing, refining, and auditing system prompts for autonomous AI agents based on Anthropic's production practices.

agentailor/fullstack-langgraph-nextjs-agent132—~3.6kAutomated safety check: PassMIT1 mo ago
612

A skill your agent uses when evaluating BitRouter route decisions or Eval Exchange subjects with task-native verifiers, human reviewers, private enterprise evaluators, agentic judges, or genuinely…

bitrouter/bitrouter235—~1.2kAutomated safety check: PassApache-2.0yesterday
613
613.Cdaf

Read CDAF sidecar files (.cdaf) instead of processing video with vision.

UditAkhourii/cdaf121—~1.9kAutomated safety check: PassMIT1 mo ago
614

Agnes AI API 接入支持与问题排查 Skill。帮助新用户完成 Agnes AI API 的接入配置, 诊断和解决接入过程中遇到的认证、参数、响应、图像生成、视频生成等各类问题。

lj1270998580-crypto/Agnes-help-skill305—~14kAutomated safety check: NotesNo licence18 days ago
615

YouTube 영상에서 쇼츠 클립 3개를 자동 제작합니다. An agent skill from uxjoseph/content-marketing-team.

uxjoseph/content-marketing-team107—~665Automated safety check: PassNo licence9 mo ago
616

Creates structured agent definitions using the 7-component format grounded in persona science (the alignment-accuracy tradeoff), vocabulary routing, and the MAST failure taxonomy + Forge watchlist.

jdforsythe/forge151—~4.5kAutomated safety check: PassMIT3 mo ago
617

SmartCrusher + CCR context compression — crunch large JSON arrays, tool outputs, and search results to save tokens.

momori777/Artemis380—~562Automated safety check: PassMIT11 days ago
618
618.Init

Turn on Rekal memory in the current repository by running rekal init.

rekal-dev/rekal-cli207—~567Automated safety check: PassApache-2.01 mo ago
619

Prepare, validate, build, and use Nemotron Customizer airgap image bundles for offline clusters.

NVIDIA-NeMo/Nemotron2.1k—~1.2kAutomated safety check: PassApache-2.05 days ago
620

Scaffold a first eval suite for an agent: mine real failures into cases, write behavioural checks over traces, and generate the runner.

undefined-ui/second-brain-os1k—~786Automated safety check: PassMITyesterday
621

A skill your agent uses when the workflow is too slow, too expensive, or both and needs latency, cost, or token usage optimization.

sharpdeveye/maestro591—~745Automated safety check: PassMIT5 mo ago
622

Prepare a macOS or Ubuntu machine for edge-e3 development, diagnose missing Verilator/LLVM/Python dependencies, initialize the public repository, and answer or act on the example prompts in the root…

exeex/edge-cores110—~1.7kAutomated safety check: NotesApache-2.015 days ago
623

Review and upgrade MetaX model support against a target vLLM revision and installed MACA components, recursively including model-dependent attention and kernels.

MetaX-MACA/vLLM-metax180—~3.2kAutomated safety check: PassApache-2.0yesterday
624

Test a model end-to-end using the xybrid execution system. An agent skill from xybrid-ai/xybrid.

xybrid-ai/xybrid469—~1.3kAutomated safety check: PassApache-2.0yesterday